scrapy-redis源码解析

1、connection.py: 建立 Redis 连接

1. SETTINGS_PARAMS_MAP: 将 Redis 参数名映射到 redis 库的参数名
2. get_redis_from_settings 函数: 从 Scrapy 的 settings 对象获取连接参数并调用 get_redis 建立 Redis 连接
3. get_redis 函数: 辅助函数，建立 Redis 连接`

import six

from scrapy.utils.misc import load_object

from . import defaults


# Shortcut maps 'setting name' -> 'parmater name'.
# 这是一个参数映射 左边是设置名称 右边是参数名称
SETTINGS_PARAMS_MAP = {
    'REDIS_URL': 'url',
    'REDIS_HOST': 'host',
    'REDIS_PORT': 'port',
    'REDIS_ENCODING': 'encoding',
}

# 获取连接redis参数
# from_settings = get_redis_from_settings
def get_redis_from_settings(settings):
    """Returns a redis client instance from given Scrapy settings object.

    This function uses ``get_client`` to instantiate the client and uses
    ``defaults.REDIS_PARAMS`` global as defaults values for the parameters. You
    can override them using the ``REDIS_PARAMS`` setting.

    Parameters
    ----------
    settings : Settings
        A scrapy settings object. See the supported settings below.

    Returns
    -------
    server
        Redis client instance.

    Other Parameters
    ----------------
    REDIS_URL : str, optional
        Server connection URL.
    REDIS_HOST : str, optional
        Server host.
    REDIS_PORT : str, optional
        Server port.
    REDIS_ENCODING : str, optional
        Data encoding.
    REDIS_PARAMS : dict, optional
        Additional client parameters.

    """
    # 将默认的redis连接参数拷贝一份给params
    params = defaults.REDIS_PARAMS.copy()
    # 如果settings中没有定义REDIS_PARAMS  则使用默认的参数
    params.update(settings.getdict('REDIS_PARAMS'))
    # XXX: Deprecate REDIS_* settings.
    # 将settings中的REDIS_URL, REDIS_HOST, REDIS_PORT, REDIS_ENCODING更新进入params中 没有则使用默认的
    for source, dest in SETTINGS_PARAMS_MAP.items():
        val = settings.get(source)
        if val:
            params[dest] = val

    # Allow ``redis_cls`` to be a path to a class.
    if isinstance(params.get('redis_cls'), six.string_types):
        params['redis_cls'] = load_object(params['redis_cls'])
    # get_redis(**params) = redis_cls(**kwargs) = redis的连接
    # from_settings() = get_redis_from_settings() = get_redis(**params) = redis_cls(**kwargs) = redis的连接
    return get_redis(**params)


# Backwards compatible alias.
from_settings = get_redis_from_settings


# 获取redis连接
def get_redis(**kwargs):
    """Returns a redis client instance.

    Parameters
    ----------
    redis_cls : class, optional
        Defaults to ``redis.StrictRedis``.
    url : str, optional
        If given, ``redis_cls.from_url`` is used to instantiate the class.
    **kwargs
        Extra parameters to be passed to the ``redis_cls`` class.

    Returns
    -------
    server
        Redis client instance.

    """
    # 从参数字典中获取redis_cls 没有则使用默认的
    # redis_cls = defaults.REDIS_CLS = Redis
    redis_cls = kwargs.pop('redis_cls', defaults.REDIS_CLS)
    url = kwargs.pop('url', None)
    if url:
        # 使用url连接redis 优先使用url
        return redis_cls.from_url(url, **kwargs)
    else:
        # 使用参数连接redis Redis(**kwargs) 返回redis连接
        return redis_cls(**kwargs)

2、defaults.py： 定义了连接redis的默认参数，定义了一系列的变量名称

import redis


# For standalone use.
DUPEFILTER_KEY = 'dupefilter:%(timestamp)s'

PIPELINE_KEY = '%(spider)s:items'

REDIS_CLS = redis.StrictRedis
REDIS_ENCODING = 'utf-8'
# Sane connection defaults.
# 默认连接redis的参数
REDIS_PARAMS = {
    'socket_timeout': 30,
    'socket_connect_timeout': 30,
    'retry_on_timeout': True,
    'encoding': REDIS_ENCODING,
}

# 存放在redis中的队列变量名称
SCHEDULER_QUEUE_KEY = '%(spider)s:requests'
# 入队的class类 默认是优先队列
SCHEDULER_QUEUE_CLASS = 'scrapy_redis.queue.PriorityQueue'
# 用于保存我们去重的key
SCHEDULER_DUPEFILTER_KEY = '%(spider)s:dupefilter'
# 实现去重的类
SCHEDULER_DUPEFILTER_CLASS = 'scrapy_redis.dupefilter.RFPDupeFilter'

# 起始url
START_URLS_KEY = '%(name)s:start_urls'
# 起始url的类型 默认是列表
START_URLS_AS_SET = False

3、dupefilter.py：实现了基于redis的request 去重

1. request_fingerprint：生成指纹的函数
2. request_seen： 将指纹添加到redis，当收到新的 request，首先生成指纹判断是否存在于已爬取的指纹库内（Redis set），若存在则返回 1，不存在返回 0，判定结果返回False，就是不重复，并把新的fingerprint加入到数据库中。

import logging
import time

from scrapy.dupefilters import BaseDupeFilter
from scrapy.utils.request import request_fingerprint

from . import defaults
from .connection import get_redis_from_settings


logger = logging.getLogger(__name__)


# TODO: Rename class to RedisDupeFilter.
class RFPDupeFilter(BaseDupeFilter):
    """Redis-based request duplicates filter.

    This class can also be used with default Scrapy's scheduler.

    """

    logger = logger

    def __init__(self, server, key, debug=False):
        """Initialize the duplicates filter.

        Parameters
        ----------
        server : redis.StrictRedis
            The redis server instance.
        key : str
            Redis key Where to store fingerprints.
        debug : bool, optional
            Whether to log filtered requests.

        """
        # 初始化redis连接
        self.server = server
        # 去重key值
        self.key = key
        # 默认false
        self.debug = debug
        self.logdupes = True

    # 类方法 cls当前类本身 RFPDupeFilter
    # 初始化init中的值
    @classmethod
    def from_settings(cls, settings):
        """Returns an instance from given settings.

        This uses by default the key ``dupefilter:<timestamp>``. When using the
        ``scrapy_redis.scheduler.Scheduler`` class, this method is not used as
        it needs to pass the spider name in the key.

        Parameters
        ----------
        settings : scrapy.settings.Settings

        Returns
        -------
        RFPDupeFilter
            A RFPDupeFilter instance.


        """
        # 获取redis的连接 默认是0库
        server = get_redis_from_settings(settings)
        # XXX: This creates one-time key. needed to support to use this
        # class as standalone dupefilter with scrapy's default scheduler
        # if scrapy passes spider on open() method this wouldn't be needed
        # TODO: Use SCRAPY_JOB env as default and fallback to timestamp.
        # defaults.DUPEFILTER_KEY = dupefilter:%(timestamp)s % {'timestamp': int(time.time())}
        key = defaults.DUPEFILTER_KEY % {'timestamp': int(time.time())}
        debug = settings.getbool('DUPEFILTER_DEBUG')
        return cls(server, key=key, debug=debug)

    @classmethod
    def from_crawler(cls, crawler):
        """Returns instance from crawler.

        Parameters
        ----------
        crawler : scrapy.crawler.Crawler

        Returns
        -------
        RFPDupeFilter
            Instance of RFPDupeFilter.

        """
        return cls.from_settings(crawler.settings)

    # 将指纹添加到redis
    def request_seen(self, request):
        """Returns True if request was already seen.

        Parameters
        ----------
        request : scrapy.http.Request

        Returns
        -------
        bool

        """
        # 产生request对应唯一的指纹
        fp = self.request_fingerprint(request)
        # This returns the number of values added, zero if already exists.
        # self.key 这是一个集合的key 添加成功返回1
        # 将指纹添加到redis数据库的集合中
        added = self.server.sadd(self.key, fp)
        # 如果added返回的是1 表示return false
        # 如果added返回的是0 表示return true
        return added == 0

    # 生产指纹的函数
    def request_fingerprint(self, request):
        """Returns a fingerprint for a given request.

        Parameters
        ----------
        request : scrapy.http.Request

        Returns
        -------
        str

        """
        # 每一个request生产一个唯一的指纹
        return request_fingerprint(request)

    @classmethod
    def from_spider(cls, spider):
        settings = spider.settings
        server = get_redis_from_settings(settings)
        dupefilter_key = settings.get("SCHEDULER_DUPEFILTER_KEY", defaults.SCHEDULER_DUPEFILTER_KEY)
        key = dupefilter_key % {'spider': spider.name}
        debug = settings.getbool('DUPEFILTER_DEBUG')
        return cls(server, key=key, debug=debug)

    def close(self, reason=''):
        """Delete data on close. Called by Scrapy's scheduler.

        Parameters
        ----------
        reason : str, optional

        """
        self.clear()

    def clear(self):
        """Clears fingerprints data."""
        # 删除self.key
        self.server.delete(self.key)

    def log(self, request, spider):
        """Logs given request.

        Parameters
        ----------
        request : scrapy.http.Request
        spider : scrapy.spiders.Spider

        """
        if self.debug:
            msg = "Filtered duplicate request: %(request)s"
            self.logger.debug(msg, {'request': request}, extra={'spider': spider})
        elif self.logdupes:
            msg = ("Filtered duplicate request %(request)s"
                   " - no more duplicates will be shown"
                   " (see DUPEFILTER_DEBUG to show all duplicates)")
            self.logger.debug(msg, {'request': request}, extra={'spider': spider})
            self.logdupes = False

4、picklecompat.py：序列化与反序列化

1. loads函数：序列化，将要插入数据库的所有的值序列化为字符串
2. dumps函数：反序列化，将要取出来的进行解码

"""A pickle wrapper module with protocol=-1 by default."""

try:
    import cPickle as pickle  # PY2
except ImportError:
    import pickle


# 将其他的需要插入数据库的值序列化字符串
def loads(s):
    return pickle.loads(s)


def dumps(obj):
    return pickle.dumps(obj, protocol=-1)

5、pipeline.py：存储数据

1. process_item函数：用线程异步存储item
2. _process_item函数：序列化item，并真正存储item的函数。settings中配置的REDIS_ITEMS_KEY作为key，把item序列化之后存入redis数据库对应的value中

from scrapy.utils.misc import load_object
from scrapy.utils.serialize import ScrapyJSONEncoder
from twisted.internet.threads import deferToThread

from . import connection, defaults


default_serialize = ScrapyJSONEncoder().encode


class RedisPipeline(object):
    """Pushes serialized item into a redis list/queue

    Settings
    --------
    REDIS_ITEMS_KEY : str
        Redis key where to store items.
    REDIS_ITEMS_SERIALIZER : str
        Object path to serializer function.

    """

    def __init__(self, server,
                 key=defaults.PIPELINE_KEY,
                 serialize_func=default_serialize):
        """Initialize pipeline.

        Parameters
        ----------
        server : StrictRedis
            Redis client instance.
        key : str
            Redis key where to store items.
        serialize_func : callable
            Items serializer function.

        """
        # redis连接
        self.server = server
        # 在设置中没有自定义 则使用默认的
        self.key = key
        # serialize_func = encode
        self.serialize = serialize_func

    # 初始化init的参数
    @classmethod
    def from_settings(cls, settings):
        # 获取redis连接参数
        params = {
            'server': connection.from_settings(settings),
        }
        # 可以自定义item在数据库中的键名
        if settings.get('REDIS_ITEMS_KEY'):
            params['key'] = settings['REDIS_ITEMS_KEY']
        # 可以自定义序列化函数名
        if settings.get('REDIS_ITEMS_SERIALIZER'):
            params['serialize_func'] = load_object(
                settings['REDIS_ITEMS_SERIALIZER']
            )

        return cls(**params)

    @classmethod
    def from_crawler(cls, crawler):
        return cls.from_settings(crawler.settings)

    def process_item(self, item, spider):
        # 为了高效 放到一个线程中去执行 存储item 是异步的 无需等待
        # 后面来的item就不会受前面的影响
        return deferToThread(self._process_item, item, spider)

    def _process_item(self, item, spider):
        # 定义出item的redis_key
        # self.key = '%(spider)s:items' % {'spider': spider.name}
        key = self.item_key(item, spider)
        # 序列化item
        data = self.serialize(item)
        # 往右边插入一条item数据 是一个列表
        self.server.rpush(key, data)
        return item

    def item_key(self, item, spider):
        """Returns redis key based on given spider.

        Override this function to use a different key depending on the item
        and/or spider.

        """
        return self.key % {'spider': spider.name}

6、queue.py：任务队列
···FifoQueue类: 继承 Base，重写了 push 和 pop 方法实现先进先出队列。

1. __len__方法：获取列表的长度。
2. push方法：将Requests对象序列化后存储到列表中。
3. pop方法：调用的rpop()方法，从列表右侧取出数据，然后反序列化为Request对象。
   Request在列表中存取的顺序是左侧进、右侧出，有序的进出，先进先出(FIFO)。

···PriorityQueue类：

1. __len__方法：调用zcard()操作返回有序集合的大小，也就是队列的长度。
2. push方法：调用了zadd()操作向集合中添加元素，这里的分数设置为Request优先级的相反数，分数低的会排在集合前面，优先级高的Request就会在集合最前面。
3. pop方法：调用了zrange()取出集合中的第一个元素，第一个元素就是优先级最高的Rquest，然后调用zremrangebyrank将这个元素删除。

···LifoQueue类：
和FifoQueue类类似，LifoQueue和FifoQueue的区别是在pop()方法使用的是lpop，也就是左侧出去。效果就是先进后出，后进先出(LIFO)

from scrapy.utils.reqser import request_to_dict, request_from_dict

from . import picklecompat


class Base(object):
    """Per-spider base queue class"""

    def __init__(self, server, spider, key, serializer=None):
        """Initialize per-spider redis queue.

        Parameters
        ----------
        server : StrictRedis
            Redis client instance.
        spider : Spider
            Scrapy spider instance.
        key: str
            Redis key where to put and get messages.
        serializer : object
            Serializer object with ``loads`` and ``dumps`` methods.

        """
        if serializer is None:
            # Backward compatibility.
            # TODO: deprecate pickle.
            serializer = picklecompat
        if not hasattr(serializer, 'loads'):
            raise TypeError("serializer does not implement 'loads' function: %r"
                            % serializer)
        if not hasattr(serializer, 'dumps'):
            raise TypeError("serializer '%s' does not implement 'dumps' function: %r"
                            % serializer)

        self.server = server
        self.spider = spider
        self.key = key % {'spider': spider.name}
        self.serializer = serializer

    def _encode_request(self, request):
        """Encode a request object"""
        obj = request_to_dict(request, self.spider)
        return self.serializer.dumps(obj)

    def _decode_request(self, encoded_request):
        """Decode an request previously encoded"""
        obj = self.serializer.loads(encoded_request)
        return request_from_dict(obj, self.spider)

    def __len__(self):
        """Return the length of the queue"""
        raise NotImplementedError

    def push(self, request):
        """Push a request"""
        raise NotImplementedError

    def pop(self, timeout=0):
        """Pop a request"""
        raise NotImplementedError

    def clear(self):
        """Clear queue/stack"""
        self.server.delete(self.key)


# 先进先出队列
class FifoQueue(Base):
    """Per-spider FIFO queue"""

    def __len__(self):
        """Return the length of the queue"""
        # 查看self.key的数量 此时的key是request队列长度
        # 需要爬取的request的数量
        return self.server.llen(self.key)

    def push(self, request):
        """Push a request"""
        # 左边插入一个元素 request需要经过一个序列化的过程 转换为字符串
        self.server.lpush(self.key, self._encode_request(request))

    def pop(self, timeout=0):
        """Pop a request"""
        if timeout > 0:
            # 队尾弹出一个数据
            data = self.server.brpop(self.key, timeout)
            if isinstance(data, tuple):
                data = data[1]
        else:
            # 队尾弹出数据
            data = self.server.rpop(self.key)
        if data:
            # 给弹出的数据解码
            return self._decode_request(data)


class PriorityQueue(Base):
    """Per-spider priority queue abstraction using redis' sorted set"""

    def __len__(self):
        """Return the length of the queue"""
        # 查看有序集合的长度 只有有序集合才可以实现优先级队列
        return self.server.zcard(self.key)

    def push(self, request):
        """Push a request"""
        # 给request解码
        data = self._encode_request(request)
        # 给request一个固定的优先级分数
        score = -request.priority
        # We don't use zadd method as the order of arguments change depending on
        # whether the class is Redis or StrictRedis, and the option of using
        # kwargs only accepts strings, not bytes.
        # 将队列插入数据库
        self.server.execute_command('ZADD', self.key, score, data)

    def pop(self, timeout=0):
        """
        Pop a request
        timeout not support in this queue class
        """
        # use atomic range/remove using multi/exec
        pipe = self.server.pipeline()
        pipe.multi()
        # 根据排名查询排名为0的数据 删除
        pipe.zrange(self.key, 0, 0).zremrangebyrank(self.key, 0, 0)
        # 执行查询命令 返回排名第一的数据 返回的是一个列表
        # count 返回的数量
        results, count = pipe.execute()
        if results:
            return self._decode_request(results[0])


# 后进先出
class LifoQueue(Base):
    """Per-spider LIFO queue."""

    def __len__(self):
        """Return the length of the stack"""
        return self.server.llen(self.key)

    def push(self, request):
        """Push a request"""
        # 从左边插一个元素
        self.server.lpush(self.key, self._encode_request(request))

    def pop(self, timeout=0):
        """Pop a request"""
        if timeout > 0:
            # 从左边弹出一个元素
            data = self.server.blpop(self.key, timeout)
            if isinstance(data, tuple):
                data = data[1]
        else:
            # 从左边弹出一个元素
            data = self.server.lpop(self.key)

        if data:
            return self._decode_request(data)


# TODO: Deprecate the use of these names.
SpiderQueue = FifoQueue
SpiderStack = LifoQueue
SpiderPriorityQueue = PriorityQueue

7、scheduler.py：任务调度器

1. open(): 调度器启动时的自动的操作，这里主要实例化了任务队列 queue 和过滤器dupefilter。
2. close(): 调度器关闭时执行的操作，清理资源。
3. enqueue_request(): 过滤 request 并加入任务队列 queue
4. next_request(): 从任务队列取出 request
   scheduler.py流程：
   scheduler负责调度各个spider的request请求，scheduler初始化时，通过settings文件读取queue和dupefilters的类型（一般用默认的），配置queue和dupefilters使用的key。每当一个request要被调度时，enqueue_request被调用，scheduler使用dupefilters来判断这个url是否重复，如果不重复，就添加到queue的容器中（先进先出，先进后出和优先级都可以，可以在settings中配置）。当调度完成时，next_request被调用，scheduler就通过queue容器的接口，取出一个request，把他发送给相应的spider，让spider进行爬取工作。
   同时我们可以看到，如果setting文件中配置了SCHEDULER_PERSIST为True，那么在爬虫关闭的时候scheduler会调用自己的flush函数把redis数据库中的判重和调度池全部清空，使得我们的爬取进度完全丢失（但是item没有丢失，item数据在另一个键中储存）。如果设置SCHEDULER_PERSIST为False，爬虫关闭后，判重池和调度池仍然存在于redis数据库中，则我们再次开启爬虫时，可以接着上一次的进度继续爬取。

import importlib
import six

from scrapy.utils.misc import load_object

from . import connection, defaults


# TODO: add SCRAPY_JOB support.
class Scheduler(object):
    """Redis-based scheduler

    Settings
    --------
    SCHEDULER_PERSIST : bool (default: False)
        Whether to persist or clear redis queue.
    SCHEDULER_FLUSH_ON_START : bool (default: False)
        Whether to flush redis queue on start.
    SCHEDULER_IDLE_BEFORE_CLOSE : int (default: 0)
        How many seconds to wait before closing if no message is received.
    SCHEDULER_QUEUE_KEY : str
        Scheduler redis key.
    SCHEDULER_QUEUE_CLASS : str
        Scheduler queue class.
    SCHEDULER_DUPEFILTER_KEY : str
        Scheduler dupefilter redis key.
    SCHEDULER_DUPEFILTER_CLASS : str
        Scheduler dupefilter class.
    SCHEDULER_SERIALIZER : str
        Scheduler serializer.

    """

    def __init__(self, server,
                 persist=False,
                 flush_on_start=False,
                 queue_key=defaults.SCHEDULER_QUEUE_KEY,
                 queue_cls=defaults.SCHEDULER_QUEUE_CLASS,
                 dupefilter_key=defaults.SCHEDULER_DUPEFILTER_KEY,
                 dupefilter_cls=defaults.SCHEDULER_DUPEFILTER_CLASS,
                 idle_before_close=0,
                 serializer=None):
        """Initialize scheduler.

        Parameters
        ----------
        server : Redis
            The redis server instance.
        persist : bool
            Whether to flush requests when closing. Default is False.
        flush_on_start : bool
            Whether to flush requests on start. Default is False.
        queue_key : str
            Requests queue key.
        queue_cls : str
            Importable path to the queue class.
        dupefilter_key : str
            Duplicates filter key.
        dupefilter_cls : str
            Importable path to the dupefilter class.
        idle_before_close : int
            Timeout before giving up.

        """
        if idle_before_close < 0:
            raise TypeError("idle_before_close cannot be negative")

        self.server = server
        self.persist = persist
        self.flush_on_start = flush_on_start
        self.queue_key = queue_key
        self.queue_cls = queue_cls
        self.dupefilter_cls = dupefilter_cls
        self.dupefilter_key = dupefilter_key
        self.idle_before_close = idle_before_close
        self.serializer = serializer
        self.stats = None

    def __len__(self):
        # 队列长度
        return len(self.queue)

    @classmethod
    def from_settings(cls, settings):
        kwargs = {
            # 是否将队列持久化 在settings中设置
            'persist': settings.getbool('SCHEDULER_PERSIST'),
            # 开始的时候是否将队列清空 在settings中设置
            'flush_on_start': settings.getbool('SCHEDULER_FLUSH_ON_START'),
            'idle_before_close': settings.getint('SCHEDULER_IDLE_BEFORE_CLOSE'),
        }

        # If these values are missing, it means we want to use the defaults.
        optional = {
            # TODO: Use custom prefixes for this settings to note that are
            # specific to scrapy-redis.
            'queue_key': 'SCHEDULER_QUEUE_KEY',
            'queue_cls': 'SCHEDULER_QUEUE_CLASS',
            'dupefilter_key': 'SCHEDULER_DUPEFILTER_KEY',
            # We use the default setting name to keep compatibility.
            'dupefilter_cls': 'DUPEFILTER_CLASS',
            'serializer': 'SCHEDULER_SERIALIZER',
        }
        for name, setting_name in optional.items():
            val = settings.get(setting_name)
            if val:
                kwargs[name] = val

        # Support serializer as a path to a module.
        if isinstance(kwargs.get('serializer'), six.string_types):
            kwargs['serializer'] = importlib.import_module(kwargs['serializer'])

        server = connection.from_settings(settings)
        # Ensure the connection is working.
        server.ping()

        return cls(server=server, **kwargs)

    @classmethod
    def from_crawler(cls, crawler):
        instance = cls.from_settings(crawler.settings)
        # FIXME: for now, stats are only supported from this constructor
        instance.stats = crawler.stats
        return instance

    def open(self, spider):
        self.spider = spider

        try:
            self.queue = load_object(self.queue_cls)(
                server=self.server,
                spider=spider,
                key=self.queue_key % {'spider': spider.name},
                serializer=self.serializer,
            )
        except TypeError as e:
            raise ValueError("Failed to instantiate queue class '%s': %s",
                             self.queue_cls, e)

        self.df = load_object(self.dupefilter_cls).from_spider(spider)

        if self.flush_on_start:
            self.flush()
        # notice if there are requests already in the queue to resume the crawl
        if len(self.queue):
            spider.log("Resuming crawl (%d requests scheduled)" % len(self.queue))

    def close(self, reason):
        if not self.persist:
            self.flush()

    def flush(self):
        self.df.clear()
        self.queue.clear()

    # 入队函数
    def enqueue_request(self, request):
        # 判断request是否已经在队列中 如果在的话 则self.df.request_seen(request) = true
        # 不在则返回false 表示新插入request
        # self.df.request_seen(request) = added == 0
        # not request.dont_filter = true  默认的情况下
        # 过滤的意思是 爬过的url 我们不再爬取了
        if not request.dont_filter and self.df.request_seen(request):
            self.df.log(request, self.spider)
            return False
        if self.stats:
            self.stats.inc_value('scheduler/enqueued/redis', spider=self.spider)
        # 将request存入redis 默认是优先级队列
        self.queue.push(request)
        return True

    # 出队函数
    def next_request(self):
        block_pop_timeout = self.idle_before_close
        # 弹出一个元素
        request = self.queue.pop(block_pop_timeout)
        if request and self.stats:
            self.stats.inc_value('scheduler/dequeued/redis', spider=self.spider)
        return request

    def has_pending_requests(self):
        return len(self) > 0

8、spiders.py：对起始url发起请求 直到起始url为空

from scrapy import signals
from scrapy.exceptions import DontCloseSpider
from scrapy.spiders import Spider, CrawlSpider

from . import connection, defaults
from .utils import bytes_to_str


class RedisMixin(object):
    """Mixin class to implement reading urls from a redis queue."""
    redis_key = None
    redis_batch_size = None
    redis_encoding = None

    # Redis client placeholder.
    server = None

    # 重写start_requests,调用next_requests
    def start_requests(self):
        """Returns a batch of start requests from redis."""
        return self.next_requests()

    def setup_redis(self, crawler=None):
        """Setup redis connection and idle signal.

        This should be called after the spider has set its crawler object.
        """
        if self.server is not None:
            return

        if crawler is None:
            # We allow optional crawler argument to keep backwards
            # compatibility.
            # XXX: Raise a deprecation warning.
            crawler = getattr(self, 'crawler', None)

        if crawler is None:
            raise ValueError("crawler is required")

        settings = crawler.settings

        if self.redis_key is None:
            self.redis_key = settings.get(
                'REDIS_START_URLS_KEY', defaults.START_URLS_KEY,
            )

        self.redis_key = self.redis_key % {'name': self.name}

        if not self.redis_key.strip():
            raise ValueError("redis_key must not be empty")

        if self.redis_batch_size is None:
            # TODO: Deprecate this setting (REDIS_START_URLS_BATCH_SIZE).
            self.redis_batch_size = settings.getint(
                'REDIS_START_URLS_BATCH_SIZE',
                settings.getint('CONCURRENT_REQUESTS'),
            )

        try:
            self.redis_batch_size = int(self.redis_batch_size)
        except (TypeError, ValueError):
            raise ValueError("redis_batch_size must be an integer")

        if self.redis_encoding is None:
            self.redis_encoding = settings.get('REDIS_ENCODING', defaults.REDIS_ENCODING)

        self.logger.info("Reading start URLs from redis key '%(redis_key)s' "
                         "(batch size: %(redis_batch_size)s, encoding: %(redis_encoding)s",
                         self.__dict__)

        self.server = connection.from_settings(crawler.settings)
        # The idle signal is called when the spider has no requests left,
        # that's when we will schedule new requests from redis queue
        crawler.signals.connect(self.spider_idle, signal=signals.spider_idle)

    def next_requests(self):
        """Returns a request to be scheduled or none."""
        # 起始url在redis中的数据类型 如果settings中没有定义 则使用默认的数据类型 是列表
        use_set = self.settings.getbool('REDIS_START_URLS_AS_SET', defaults.START_URLS_AS_SET)
        # fetch_one是列表的方法
        fetch_one = self.server.spop if use_set else self.server.lpop
        # XXX: Do we need to use a timeout here?
        found = 0
        # TODO: Use redis pipeline execution.
        while found < self.redis_batch_size:
            # self.redis_ke取出一个url
            data = fetch_one(self.redis_key)
            if not data:
                # Queue empty.
                # 没有起始url的情况
                break
                # 有url的情况  发起请求
            req = self.make_request_from_data(data)
            if req:
                yield req
                found += 1
            else:
                self.logger.debug("Request not made from data: %r", data)

        if found:
            self.logger.debug("Read %s requests from '%s'", found, self.redis_key)

    def make_request_from_data(self, data):
        """Returns a Request instance from data coming from Redis.

        By default, ``data`` is an encoded URL. You can override this method to
        provide your own message decoding.

        Parameters
        ----------
        data : bytes
            Message from redis.

        """
        url = bytes_to_str(data, self.redis_encoding)
        return self.make_requests_from_url(url)

    def schedule_next_requests(self):
        """Schedules a request if available"""
        # TODO: While there is capacity, schedule a batch of redis requests.
        for req in self.next_requests():
            self.crawler.engine.crawl(req, spider=self)

    def spider_idle(self):
        """Schedules a request if available, otherwise waits."""
        # XXX: Handle a sentinel to close the spider.
        self.schedule_next_requests()
        raise DontCloseSpider


class RedisSpider(RedisMixin, Spider):
    """Spider that reads urls from redis queue when idle.

    Attributes
    ----------
    redis_key : str (default: REDIS_START_URLS_KEY)
        Redis key where to fetch start URLs from..
    redis_batch_size : int (default: CONCURRENT_REQUESTS)
        Number of messages to fetch from redis on each attempt.
    redis_encoding : str (default: REDIS_ENCODING)
        Encoding to use when decoding messages from redis queue.

    Settings
    --------
    REDIS_START_URLS_KEY : str (default: "<spider.name>:start_urls")
        Default Redis key where to fetch start URLs from..
    REDIS_START_URLS_BATCH_SIZE : int (deprecated by CONCURRENT_REQUESTS)
        Default number of messages to fetch from redis on each attempt.
    REDIS_START_URLS_AS_SET : bool (default: False)
        Use SET operations to retrieve messages from the redis queue. If False,
        the messages are retrieve using the LPOP command.
    REDIS_ENCODING : str (default: "utf-8")
        Default encoding to use when decoding messages from redis queue.

    """

    @classmethod
    def from_crawler(self, crawler, *args, **kwargs):
        obj = super(RedisSpider, self).from_crawler(crawler, *args, **kwargs)
        obj.setup_redis(crawler)
        return obj


class RedisCrawlSpider(RedisMixin, CrawlSpider):
    """Spider that reads urls from redis queue when idle.

    Attributes
    ----------
    redis_key : str (default: REDIS_START_URLS_KEY)
        Redis key where to fetch start URLs from..
    redis_batch_size : int (default: CONCURRENT_REQUESTS)
        Number of messages to fetch from redis on each attempt.
    redis_encoding : str (default: REDIS_ENCODING)
        Encoding to use when decoding messages from redis queue.

    Settings
    --------
    REDIS_START_URLS_KEY : str (default: "<spider.name>:start_urls")
        Default Redis key where to fetch start URLs from..
    REDIS_START_URLS_BATCH_SIZE : int (deprecated by CONCURRENT_REQUESTS)
        Default number of messages to fetch from redis on each attempt.
    REDIS_START_URLS_AS_SET : bool (default: True)
        Use SET operations to retrieve messages from the redis queue.
    REDIS_ENCODING : str (default: "utf-8")
        Default encoding to use when decoding messages from redis queue.

    """

    @classmethod
    def from_crawler(self, crawler, *args, **kwargs):
        obj = super(RedisCrawlSpider, self).from_crawler(crawler, *args, **kwargs)
        obj.setup_redis(crawler)
        return obj

scrapy-redis总体思路：
通过重写scheduler和spider类，实现了调度、spider启动和redis的交互。实现新的dupefilter和queue类，达到了判重和调度容器和redis的交互，因为每个主机上的爬虫进程都访问同一个redis数据库，所以调度和判重都统一进行统一管理，达到了分布式爬虫的目的。
当spider被初始化时，同时会初始化一个对应的scheduler对象，这个调度器对象通过读取settings，配置好自己的调度容器queue和判重工具dupefilter。每当一个spider产出一个request的时候，scrapy内核会把这个reuqest递交给这个spider对应的scheduler对象进行调度，scheduler对象通过访问redis对request进行判重，如果不重复就把他添加进redis中的调度池。当调度条件满足时，scheduler对象就从redis的调度池中取出一个request发送给spider，让他爬取。当spider爬取的所有暂时可用url之后，scheduler发现这个spider对应的redis的调度池空了，于是触发信号spider_idle，spider收到这个信号之后，直接连接redis读取strart url池，拿去新的一批url入口，然后再次重复上边的工作。